Drive a repository on autopilot through its GitHub issue tracker. Pick the next ordered epic/child issue, or seed a new epic only from a real code/spec/research gap, implement it on a branch, run an adversarial critic/fix loop until no actionable findings…
mihaelamj/skills
SkillsMP has collected 20 skills from mihaelamj/skills. Open a skill to review its source and details.
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 20
- GitHub stars
- 1
- GitHub forks
- 0
Skills in this repository
Showing 20 of 20 collected skills.
End-to-end workflow for fixing a tracked bug. Issue-first, branch, implement, push, PR, then a critic-fix loop that does NOT stop until the critic surfaces literally nothing new AND tests pass. Use when the user says "start on
Two Claude Code sessions coordinate via a shared JSONL chat file at ~/Downloads/claude-chat.jsonl, push-style via the Monitor tool. Lighter than /multi-claude:paired-branches; no branches, no worktrees, just a chat channel. Use when two sessions need to talk…
Spin up two Claude Code sessions on different branches of the same repo (typically main + develop), coordinating through a shared JSONL chat file in ~/Downloads. The human (U) types directives in plain English into either tab. This file is the canonical,…
Pick the next open GitHub issue to fix, ranked by severity (High > Medium > Low > decision-needed), then hand off to the `fix-bug` skill. Use when the user says "next bug", "what's next", "pick the next one", "do the next one by severity", or anything that…
Review the current repository pull request as a harsh critic, fix every actionable finding, verify the fixes, and repeat the critic/fix loop until no actionable findings remain. Use when the user asks to review, criticize, harden, or autopilot a PR or current…
Run the full cupertino post-promote verification pipeline. Clean → build → test → 3 CI guards → mock-ai-agent → 27-command CLI smoke → MCP tool probe → DB integrity. Optional --deep adds the canonical-type wrong-winner audit, BUG 5 scope check, and…
Set up swift-openapi-generator for a client target (URLSession or AsyncHTTPClient). Use when adding a new client that consumes an openapi.yaml.
Add an endpoint to openapi.yaml with request/response wiring and regenerate. Use when defining a new operation.
Wire a client or server OpenAPI middleware (auth, logging, caching, retry). Use for cross-cutting concerns on a generated client or server.
Add a schema to openapi.yaml and regenerate the Swift type. Use when defining a new request/response type.
Set up swift-openapi-generator for a server target (Vapor or Hummingbird). Use when adding a new server that serves an openapi.yaml.
Strip PII from sample API payloads (names, emails, phones, IDs, IBANs, addresses) before committing sample data. Use before checking fixtures into a repo.
Look up an OpenAPI-First Swift recipe (middleware, multi-file specs, mock transports, error handling) by example. Use when the user describes a pattern they want to apply.
Deploy a mock server generated from openapi.yaml (local via ngrok, remote, or cloud). Use to test a client without a real backend.
Install a git-commit-count build-number system (BuildNumberGenerator + BuildNumberPlugin + AppVersion) in a Swift monorepo. Use when adding a versioning surface to a package that doesn't have one.
Scaffold a new UI component into its component package, conforming to the Component protocol. Use when adding a reusable component (never in a feature package or screen).
Add an ExtremePackaging-compliant SPM target to Package.swift with the right layer and downward-only dependencies. Use when adding a new foundation/infrastructure/feature package.
Audit Package.swift for ExtremePackaging layer compliance (downward-only deps, no cycles, no feature-to-feature). Use before merging any package-graph change.
Look up an ExtremePackaging recipe (DI, ViewModels, layering, testing) by example. Use when the user describes a pattern they want to apply.